© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 157555
    Prev
    Next
    INDEX
    Explanations

    medical contexts and definitions

    np_acts-logits-general · gemini-2.5-flash-lite

    importance and expected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’)
    0.53
    િ
    0.52
    ’).
    0.48
    ’,
    0.45
    ‌ها
    0.45
    ’;
    0.44
    高
    0.44
    ‌های
    0.44
    ’),
    0.43
    ’.
    0.43
    POSITIVE LOGITS
    RelativeTo
    0.51
    ibration
    0.50
     relativo
    0.48
    UCI
    0.46
    取り寄せ
    0.46
     Pala
    0.46
    opaedic
    0.45
    TrackedDevice
    0.45
    瞟
    0.44
    ProtectedRoute
    0.44
    Activations Density 0.001%

    No Known Activations